Pyron has a built-in assistant you can ask for help in plain language. It reads the entries you already have access to, answers questions about them, and drafts changes — a new form, a report, an automation — that you review before anything takes effect.
Where the assistant lives
The assistant turns up in two places. Inside an editor — the form builder, the report editor, the flow-graph editor, or a dashboard widget editor — it sits in a panel beside what you are working on, so you can ask it to reshape that form, report or automation and watch the result take shape. Anywhere else in Pyron, you can open it as a chat panel to ask a question or start something new.
The panel collapses to a slim edge and reopens when you want it. Collapsing it keeps your conversation, so a reply that is still coming through is not lost.
From the app-wide assistant you can also begin from nothing: describe the form, report or automation you have in mind, and Pyron creates it and opens its editor with the assistant already alongside, ready to keep refining it.
What it can do
The assistant does two broad kinds of work: it answers questions about your data, and it drafts changes you can apply.
It can also search the web for what is true today: what another service's API allows, its prices and terms, a pay rate or a rule. It reads the page it found, and every fact it takes from the web links the page it came from. Each search counts towards your AI usage, like the rest of the assistant's work.
It can tell you how Pyron itself works, too. Ask what a button or a menu option does, how to do something, or where a setting lives, and it answers from Pyron's own description of its controls and pages, then from these help pages. To ask about one control, press Explain beside the attach button, then click the button or menu option you mean: the click does nothing else, and the assistant says what it does and whether you can use it. Press Escape to stop pointing. For a question neither answers, such as what happens in an unusual case, it checks how Pyron behaves, which takes about a minute. It always answers in plain words and never shows Pyron's code.
Ask a question and it looks through your entries to answer — matching both on the words you used and on meaning, so it can surface entries that are about what you asked even when they are worded differently (see Search). It can reply with a short table or a summary card built from what it found, not only a paragraph.
When you ask it to build or change something, it can:
- Put together or adjust a form, including the fields people fill in — see Building forms with the assistant.
- Draft a report template — see Drafting templates with the assistant.
- Set up an automation that runs on its own once you turn it on. An automation can search the web as it runs, for example to log each new government tender, and every result it keeps carries its link.
- Add or rework a widget on a dashboard.
The assistant knows where your workspace is and the money it counts in, from Setup → Organisation → Location. It names the place when it looks something up, so a pay rate or a rule is the one that applies to you, and it says amounts in your currency. An administrator can change it there.
Before it plans something that depends on another service, the assistant checks what that service allows today rather than relying on memory. If the only way to do what you asked would break that service's own terms, such as reading another company's posts on a site you sign in to, it tells you once, plainly, with what you would risk. Then it does what you decide.
What it acts on depends on where you opened it. Open it inside the form builder and it works on that form; open it beside a dashboard widget and it works on that widget.
Changes you approve
The assistant never changes your work behind your back. When it wants to change something, it proposes the change on a card in the conversation. The card says what the change would do. Pyron works that out by trying the change on your data first and keeping nothing. Select Apply to make the change, or Discard to drop it.
Some changes are safe to make straight away. A change like that deletes nothing, changes nothing a person made, sends nothing out of Pyron, gives no one new access and publishes nothing. The assistant makes it at once, and the card shows what was done, with links to what it made. Every other change waits for you.
If anything changes between reading a card and selecting Apply, Pyron does not make the change. The card says so and shows what the change would do now. Read it again, and apply it if you still want it.
A form the assistant drafts is different: it opens in the form builder for you to look over, and nothing is kept until you save. See Drafting forms with the assistant.
The same card shows whenever Pyron needs your approval: when you publish a page, switch an automation on or take a project live, and when the assistant has fixed an automation that stopped working, in your Inbox. If the change lets something do what it could not do before, the card lists it under New powers.
Privacy and guardrails
The assistant can only see what you can see. It reads your data through the same access rules as the rest of Pyron — your role and anything shared with you — so two people asking the same question can get different answers depending on which parts of the directory they can open. Asking the assistant never reveals anything you could not already reach yourself.
Every message to and from the assistant passes through guardrails. They screen for unsafe content, block secrets such as access keys, and mask sensitive numbers like payment-card numbers. Your administrator chooses how strict these rails are — see AI guardrails.
The assistant runs on Pyron's AWS Bedrock, and an administrator chooses the models it uses. If your data needs to stay in Australia, the models can be set so that requests are processed there — see AI models. To keep usage predictable, an administrator can also set what AI may spend each month (see AI usage and budgets).